Explaining optical flow events with parameterized spatio-temporal models
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10636919) , 326-332
- https://doi.org/10.1109/cvpr.1999.786959
Abstract
A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-temporal models may be non-linear or stochastic and are event-specific in that they characterize a particular type of object motion (e.g. sitting or walking). Within a Bayesian framework we seek the appropriate model, phase, rate, spatial position, and scale to account for the image variation. The posterior distribution over this parameter space conditioned on image measurements is typically non-Gaussian. The distribution is represented using factored sampling and is predicted and updated over time using the condensation algorithm. The resulting framework automatically detects, localizes, and recognizes motion events.Keywords
This publication has 13 references indexed in Scilit:
- Detecting activitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Cardboard people: a parameterized model of articulated image motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learned temporal models of image motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Finding periodicity in space and timePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Tracking people with twists and exponential mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Parameterized modeling and recognition of activitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Visual motion estimation and prediction: a probabilistic network model for temporal coherencePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Temporal multi-scale models for flow and accelerationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image MotionInternational Journal of Computer Vision, 1997
- Analyzing and recognizing walking figures in XYTPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994